Can I read Planning in Dynamic Environments with Conditional Autoregressive Models on EtoBox?

Planning in Dynamic Environments with Conditional Autoregressive Models by Hansen, Johanna; Kastner, Kyle; Courville, Aaron; Dudek, Gregory is a scholarly article available to read on EtoBox.

What is Planning in Dynamic Environments with Conditional Autoregressive Models about?

We demonstrate the use of conditional autoregressive generative models (van den Oord et al., 2016a) over a discrete latent space (van den Oord et al., 2017b) for forward planning with MCTS. In order to test this method, we introduce a new environment featuring varying difficulty levels, along with moving goals and obstacles. The combination of high-quality frame generation and classical planning approaches nearly matches true environment performance for our task, demonstrating the usefulness of this method for model-based planning in dynamic environments.

Author

Hansen, Johanna; Kastner, Kyle; Courville, Aaron; Dudek, Gregory

Published

2018

Language

EN